fixed and improved with github code help

app.py

@@ -1,27 +1,31 @@
 import streamlit as st
 import yfinance as yf
 import requests
-import pandas as pd
-from langchain.agents import initialize_agent, AgentType
-from langchain.tools import Tool
-from langchain_huggingface import HuggingFacePipeline
 import os
 from dotenv import load_dotenv
+from langchain.agents import Tool, AgentExecutor, LLMSingleActionAgent, AgentOutputParser
+from langchain.prompts import BaseChatPromptTemplate
+from langchain.tools import Tool
+from langchain_huggingface import HuggingFacePipeline
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from langchain.memory import ConversationBufferWindowMemory
 import torch
+import re
+from typing import List, Union
 
 # Load environment variables from .env
 load_dotenv()
+
 NEWSAPI_KEY = os.getenv("NEWSAPI_KEY")
 access_token = os.getenv("API_KEY")
 
+# Check if the access token and API key are present
+if not NEWSAPI_KEY or not access_token:
+    raise ValueError("NEWSAPI_KEY or API_KEY not found in .env file.")
+
 # Initialize the model and tokenizer for the HuggingFace pipeline
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", token=access_token)
-model = AutoModelForCausalLM.from_pretrained(
-    "google/gemma-2b-it",
-    torch_dtype=torch.bfloat16,
-    token=access_token
-)
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", torch_dtype=torch.bfloat16)
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512)
 
 # Define functions for fetching stock data, news, and moving averages
@@ -54,9 +58,6 @@ def calculate_moving_average(ticker, window=5):
     hist[f"{window}-day MA"] = hist["Close"].rolling(window=window).mean()
     return hist[["Close", f"{window}-day MA"]].tail(5)
 
-# Initialize HuggingFace pipeline
-llm = HuggingFacePipeline(pipeline=pipe)
-
 # Define LangChain tools
 stock_data_tool = Tool(
     name="Stock Data Fetcher",
@@ -78,15 +79,88 @@ moving_average_tool = Tool(
 
 tools = [stock_data_tool, stock_news_tool, moving_average_tool]
 
-# Initialize the LangChain agent
-agent = initialize_agent(
+# Set up a prompt template with history
+template_with_history = """You are SearchGPT, a professional search engine who provides informative answers to users. Answer the following questions as best you can. You have access to the following tools:
+
+{tools}
+
+Use the following format:
+
+Question: the input question you must answer
+Thought: you should always think about what to do
+Action: the action to take, should be one of [{tool_names}]
+Action Input: the input to the action
+Observation: the result of the action
+... (this Thought/Action/Action Input/Observation can repeat N times)
+Thought: I now know the final answer
+Final Answer: the final answer to the original input question
+
+Begin! Remember to give detailed, informative answers
+
+Previous conversation history:
+{history}
+
+New question: {input}
+{agent_scratchpad}"""
+
+# Set up the prompt template
+class CustomPromptTemplate(BaseChatPromptTemplate):
+    template: str
+    tools: List[Tool]
+    
+    def format_messages(self, **kwargs) -> str:
+        intermediate_steps = kwargs.pop("intermediate_steps")
+        thoughts = ""
+        for action, observation in intermediate_steps:
+            thoughts += action.log
+            thoughts += f"\nObservation: {observation}\nThought: "
+            
+        kwargs["agent_scratchpad"] = thoughts
+        kwargs["tools"] = "\n".join([f"{tool.name}: {tool.description}" for tool in self.tools])
+        kwargs["tool_names"] = ", ".join([tool.name for tool in self.tools])
+        formatted = self.template.format(**kwargs)
+        return [HumanMessage(content=formatted)]
+    
+prompt_with_history = CustomPromptTemplate(
+    template=template_with_history,
     tools=tools,
-    llm=llm,
-    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
-    verbose=True,
-    handle_parsing_errors=True
+    input_variables=["input", "intermediate_steps", "history"]
+)
+
+# Custom output parser
+class CustomOutputParser(AgentOutputParser):
+    def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:
+        if "Final Answer:" in llm_output:
+            return AgentFinish(
+                return_values={"output": llm_output.split("Final Answer:")[-1].strip()},
+                log=llm_output,
+            )
+        regex = r"Action: (.*?)[\n]*Action Input:[\s]*(.*)"
+        match = re.search(regex, llm_output, re.DOTALL)
+        if not match:
+            raise ValueError(f"Could not parse LLM output: `{llm_output}`")
+        action = match.group(1).strip()
+        action_input = match.group(2)
+        return AgentAction(tool=action, tool_input=action_input.strip(" ").strip('"'), log=llm_output)
+    
+output_parser = CustomOutputParser()
+
+# Initialize HuggingFace pipeline
+llm = HuggingFacePipeline(pipeline=pipe)
+
+# LLM chain
+llm_chain = LLMChain(llm=llm, prompt=prompt_with_history)
+tool_names = [tool.name for tool in tools]
+agent = LLMSingleActionAgent(
+    llm_chain=llm_chain, 
+    output_parser=output_parser,
+    stop=["\nObservation:"], 
+    allowed_tools=tool_names
 )
 
+memory = ConversationBufferWindowMemory(k=2)
+agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True, memory=memory)
+
 # Streamlit app
 st.title("Trading Helper Agent")
 
@@ -98,7 +172,7 @@ if st.button("Submit"):
         with st.spinner("Processing..."):
             try:
                 # Run the agent and get the response
-                response = agent.run(query)  # Correct method is `run()`
+                response = agent_executor.run(query)  # Correct method is `run()`
                 st.success("Response:")
                 st.write(response)
             except Exception as e: